Housing Search logo

Housing Search

Community
spyrae
housing-search

Find somewhere to stay across listing sites, compare on total cost, and ask the questions a listing never answers.

Overview

Publisherspyrae
Repositorykronos-agent-os
Skill namehousing-search
Stars
66
Forks
14
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by spyrae on GitHub. Read the source before you install it.

Installation

Install the Housing Search AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/spyrae/kronos-agent-os/tree/main/templates/skill-packs/marketplace/skills/housing-search
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/spyrae/kronos-agent-os.git /tmp/kronos-agent-os
mkdir -p .claude/skills
cp -r /tmp/kronos-agent-os/templates/skill-packs/marketplace/skills/housing-search .claude/skills/housing-search
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Housing Search in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Housing Search on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Housing Search is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Housing Search

Before searching

Six answers, and searching without them wastes the search:

  1. Dates and length of stay. A month is a different market from a week — monthly rates on the big platforms run far below thirty nightly rates, and a search priced per night answers a question nobody asked.
  2. Total budget, not the nightly figure. The number that matters is rent for the whole stay plus deposit plus utilities plus fees.
  3. Area, at the granularity the owner actually cares about.
  4. Non-negotiables — the two or three things whose absence rules a place out (air conditioning, a desk, a kitchen, parking).
  5. Who is staying — children, pets and long-stay guests all change what is available and what it costs.
  6. When they need to decide. It changes whether to shortlist three or thirty.

Anything the owner has told you before lives in notes/user/. Ask only for what is missing, and ask once.

Searching

Search each site separately and in parallel; they overlap less than people expect. Fetch listing pages with fetch_page — search-result pages reorder themselves and are worth less than they look.

Signed in, prices and availability differ. If the owner has an account for the site, open it first (open_site_session) and say in the result whether you were signed in — an unsigned search is a different set of prices, and presenting it as theirs is a small lie that compounds.

What a listing does not tell you

Collect these per candidate, and never fill one in by assumption. A listing that does not state the deposit is not a listing with no deposit; a missing figure is not a zero one, and treating it as one puts the least documented place at the top of the list:

  • deposit: amount, and what returns it
  • utilities: who pays, and what they actually run to in the hot or cold season
  • minimum stay, and what leaving early costs
  • what is not included — cleaning, linen, agency fee, tourist tax
  • who repairs what, and how quickly
  • internet: the real speed, not the advertised one

Red flags

Worth naming to the owner rather than silently down-ranking:

  • no photo of the bathroom or the kitchen
  • reviews that all appear within one week, or none at all
  • a price far below the cluster for that area, with nothing in the listing explaining why
  • the location shown only as a district
  • the same photographs appearing on other listings
  • pressure to move the conversation or the payment off the platform

Comparing

Use compare_offers: recurring costs are rent and utilities, one-off costs are deposit, cleaning and fees, and periods is the number of months. It ranks on money and refuses to rank a listing missing a cost — which is the correct outcome, not a gap to paper over.

Then judge the rest yourself, out loud: a place ten minutes further out for a third less is a trade the owner makes, not the arithmetic.

Waiting

Enquiries take days. Do not hold the conversation open — start a plan (plan_start), add a step per landlord, and a comparison step that depends on all of them. A landlord who never answers fails their step; the comparison still runs, with that absence stated.

Output

  • Shortlist, ranked by total cost for the whole stay, with the arithmetic shown
  • What is unknown per listing, and what you asked
  • Red flags, named
  • Your recommendation and the tradeoff it accepts

Frequently asked questions

What does the Housing Search AI skill do?

Find somewhere to stay across listing sites, compare on total cost, and ask the questions a listing never answers.

Why use Housing Search on TypingMind?

Because you install it once and use it with any model. Housing Search is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Housing Search in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/spyrae/kronos-agent-os/tree/main/templates/skill-packs/marketplace/skills/housing-search. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Housing Search?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Housing Search?

As many as you like. As long as a model supports skills, you can use Housing Search with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Housing Search AI skill free?

Yes. It is published on GitHub by spyrae under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇